Using Feature Interaction among GPS Data for Road Intersection Detection

Road intersection plays a vital role in road network construction, automatic drive, and intelligent transportation systems. Most methods detect road intersections only using geometrical features without spatio-temporal features, leading to insufficient precision. In addition, the existing methods do not consider the impact of feature interaction. For the issue, this paper proposes a novel way to detect road intersections based on GPS trajectory by extracting spatio-temporal features and using the interaction of the features to enhance the precision of the detection. The proposed method is implemented on DIDI's GPS data in Chengdu. The performance shows that the proposed method can effectively improve the precision of road intersection detection compared with the existing method, which is beneficial for road network construction and makes up for the deficiency of existing methods.

[1]  Xing Xie,et al.  xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems , 2018, KDD.

[2]  Jing Wang,et al.  Automatic intersection and traffic rule detection by mining motor-vehicle GPS trajectories , 2017, Comput. Environ. Urban Syst..

[3]  Wang Xiaoqin,et al.  Auto-extraction of road intersection from high resolution remote sensing image , 2015 .

[4]  Haihong Zhu,et al.  Extraction of Road Intersections from GPS Traces Based on the Dominant Orientations of Roads , 2017, ISPRS Int. J. Geo Inf..

[5]  Hamid K. Aghajan,et al.  Detecting Road Intersections from GPS Traces Using Longest Common Subsequence Algorithm , 2017, ISPRS Int. J. Geo Inf..

[6]  Steffen Rendle,et al.  Factorization Machines , 2010, 2010 IEEE International Conference on Data Mining.

[7]  ShahabiCyrus,et al.  Automatic and Accurate Extraction of Road Intersections from Raster Maps , 2009 .

[8]  Minshi Liu,et al.  Map Matching for Urban High-Sampling-Frequency GPS Trajectories , 2020, ISPRS Int. J. Geo Inf..

[9]  Xing Xie,et al.  xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems , 2018, Knowledge Discovery and Data Mining.

[10]  Craig A. Knoblock,et al.  Automatic and Accurate Extraction of Road Intersections from Raster Maps , 2008, GeoInformatica.

[11]  Huang Rui,et al.  Recent progress in taxi trajectory data mining , 2019 .

[12]  Guangluan Xu,et al.  Extended Classification Course Improves Road Intersection Detection from Low-Frequency GPS Trajectory Data , 2020, ISPRS Int. J. Geo Inf..

[13]  M. E. Khalifa,et al.  Building road segments and detecting turns from GPS tracks , 2018, J. Comput. Sci..

[14]  John Krumm,et al.  From GPS traces to a routable road map , 2009, GIS.

[15]  Longgang Xiang,et al.  An Intersection-First Approach for Road Network Generation from Crowd-Sourced Vehicle Trajectories , 2019, ISPRS Int. J. Geo Inf..

[16]  Tat-Seng Chua,et al.  Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks , 2017, IJCAI.

[17]  Yunming Ye,et al.  DeepFM: A Factorization-Machine based Neural Network for CTR Prediction , 2017, IJCAI.

[18]  Tang Luliang,et al.  Urban Intersection Recognition and Construction Based on Big Trace Data , 2017 .

[19]  Liang Wang,et al.  Detecting Road Intersections from Coarse-gained GPS Traces Based on Clustering , 2013, J. Comput..

[20]  James Biagioni,et al.  Inferring Road Maps from Global Positioning System Traces , 2012 .

[21]  Yang Min,et al.  Decision tree model for extracting road intersection feature from vehicle trajectory data , 2019 .

[22]  Min Deng,et al.  Generating urban road intersection models from low-frequency GPS trajectory data , 2018, Int. J. Geogr. Inf. Sci..

[23]  Wilfried Philips,et al.  Road Intersection Detection through Finding Common Sub-Tracks between Pairwise GNSS Traces , 2017, ISPRS Int. J. Geo Inf..